Abstract
Handwritten digit or character recognition is the primary task of researching in the field of OCR system. But handwritten digit recognition is a complex task due to the variation of training image size and handwritten style. This paper presents how the nature of the motion of the digit recognition model changes based on different pixel images. We have proposed a 12-layer Convolutional Neural Network (CNN) using four different pixel handwritten images such as 24 × 24, 28 × 28, 32 × 32, and 36 × 36. All fundamental steps such as dataset collection, dataset preparation, detail architecture of CNN, and hyperparameter optimization are described briefly in this paper. The goal of this study is to provide a clear insight into CNN hyperparameters, CNN architecture, images of different pixels on which the effectiveness of the model depends. In this research, we have used two publicly available datasets named CMATERDB 3.1.1 and BanglaLekha-Isolated. The proposed method has achieved a validation accuracy of 99.50% for the CMATERDB 3.1.1 dataset and 98.85% for the BanglaLekha-Isolated dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shamim, S., Miah, M. B. A., Sarker, A., Rana, M., and Jobair, A. A. (2018). Handwritten Digit Recognition using Machine Learning Algorithms. Global Journal of Computer Science and Technology: D Neural & Artificial Intelligence. Volume 18.
Sufiana, A., Ghosh, A., Naskar, A., and Sultana, F. (2020). BDNet: Bengali Handwritten Numeral Digit Recognition based on Densely connected Convolutional Neural Networks. HafizurRahman. Journal of King Saud University - Computer and Information Sciences.
https://en.wikipedia.org/wiki/Automatic_number-plate_recognition, last accessed 5 October 2020.
https://brta.portal.gov.bd/sites/default/files/files/brta.portal.gov.bd/monthly_report/d4d56177_644f_44f8_99c4_3417b3d7b0f4/MV_statistics-bangladesh-March-18.pdf, last accessed 6 October 2020.
Bhattacharya, U., and Chaudhuri, B. B. (2009). Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals. IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume: 31, Issue: 3.
Biswas, M., Islam, R., Shom, G. K., Shopon, M., Mohammed, N., Momen, S., and Abedin, A. (2017). BanglaLekha-Isolated: A multi-purpose comprehensive dataset of Handwritten Bangla Isolated characters.
Rahman, M. M., Akhand, M. A. H., Islam, S., & Shill, P. C. (2015). Bangla Handwritten Character Recognition using Convolutional Neural Network. I.J: Image, Graphics and Signal Processing. https://doi.org/10.5815/ijigsp.2015.08.0.
Alom, M. Z., Sidike, P., Hasan, M., Taha, T. M., and Asari, V. K. (2018). Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks. https://doi.org/10.1155/2018/6747098
Rabby, A. S. A., Abujar, S., Haque, S., and Hossain, S. A. (2018). Bangla Handwritten Digit Recognition Using Convolutional Neural Network. Emerging Technologies in Data Mining and Information Security, Advances in Intelligent Systems and Computing 755, https://doi.org/10.1007/978-981-13-1951-8_11
Chowdhury, R. R., Hossain, M. S., Islam, R. U., Andersson, K., and Hossain, S. (2019). Bangla Handwritten Character Recognition using Convolutional Neural Network with Data Augmentation, 8th International Conference on Informatics, Electronics & Vision (ICIEV).
Saha, C., Faisal, R. H., and Rahman, M. M. (2019). Bangla Handwritten Digit Recognition Using anImproved Deep Convolutional Neural NetworkArchitecture. International Conference on Electrical, Computer and Communication Engineering (ECCE.
Ahlawat, S., Choudhary, A., Nayyar, A., Singh, S., & Yoon, B. (2020). Improved Handwritten Digit Recognition UsingConvolutional Neural Networks (CNN). MDPI journals. https://doi.org/10.3390/s20123344.
Bharadwaj, Y. S., Rajaram P., Sriram V. P., Sudhakar, S., and Prakash, K. B. (2020). Effective Handwritten Digit Recognition using Deep Convolution Neural Network. International Journal of Advanced Trends in Computer Science and Engineering. Volume 9 No.2.
Hakim, S. M. A, and Asaduzzaman. (2019) Handwritten Bangla Numeral and Basic Character Recognition Using Deep Convolutional Neural Network. International Conference on Electrical, Computer and Communication Engineering (ECCE).
https://www.sciencedirect.com/science/article/pii/S2352340917301117, last accessed 5 October, 2020.
https://www.youtube.com/watch?v=_U68MQKQljs, last accessed 12 September, 2020.
Kumar, T., and Verma, K. (2010). A Theory Based on Conversion of RGB image to Gray image. International Journal of Computer Applications (0975 – 8887), Volume 7– No.2.
https://machinelearningmastery.com/why-one-hot-encode-data-in-machine-learning/, last accessed 25 September 2020.
Ahlawat, S., Batra, V., Banerjee, S., Saha, J., and Garg, A. K. (2018). Hand Gesture Recognition Using Convolutional Neural Network. On proceedings of International Conference on Innovative Computing and Communication. Lecture Notes in Networks and Systems, 179–186. https://doi.org/10.1007/978-981-13-2354-6_20
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2014). A simple way to prevent neural networks from overfitting. Journal of Machine Learing Research, Volume-15(56):1929 − 1958.
Hamed, M., & Desouky, A. A. E. (1996). Effect of Learning Rate on the Recognition of Images.. https://doi.org/10.1155/1996/45086.
Janocha, K., and Czarnecki, W.M. (2017). On Loss Functions for Deep Neural Networks in Classification. Theoretical Foundations of Machine Learning arXiv:1702.05659.
Banerjee, C., Mukherjee, T., & Pasiliao, E. (2019). An Empirical Study on Generalizations of the ReLU Activation Function. ACM Southeast Conference, DOI, 10(1145/3299815), 3314450.
Khan, H. A., Helal, A. A., and Ahmed, K. I. (2014). Handwritten Bangla digit recognition using sparse rep-resentation classifier. In: International Conference on Informatics, Electronics & Vision(ICIEV), pp. 1–6.
Hassan, T., and Khan, H. A. (2015). Handwritten Bangla numeral recognition using local binary pattern. In: International Conference on Electrical Engineering and Information CommunicationTechnology (ICEEICT), pp. 1–4.
Sarkhel, R., Das, N., Saha, A. K., and Nasipuri, M. (2016). A multi-objective approach towards cost-effective isolated handwritten Bangla character and digit recognition. Pattern Recognition, Volume 58, Issue C, https://doi.org/10.1016/j.patcog.2016.04.010.
Sharif, S. M. A., Mohammed, N., Mansoor, N., and Momen, S. (2016). A hybrid deep model with HOG fea-tures for Bangla handwritten numeral classification. In: 9th International Conference onElectrical and Computer Engineering (ICECE), pp. 463–466.
Purkaystha, B., Datta, T., and Islam, M. S. (2017). Bengali handwritten character recognition using deep convolutional neural network. 20th International Conference of Computer and Information Technology (ICCIT).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Naim, F.A. (2022). Bangla Handwritten Digit Recognition Based on Different Pixel Matrices. In: Khanna, A., Gupta, D., Bhattacharyya, S., Hassanien, A.E., Anand, S., Jaiswal, A. (eds) International Conference on Innovative Computing and Communications. Advances in Intelligent Systems and Computing, vol 1387. Springer, Singapore. https://doi.org/10.1007/978-981-16-2594-7_27
Download citation
DOI: https://doi.org/10.1007/978-981-16-2594-7_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2593-0
Online ISBN: 978-981-16-2594-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)